OdorAgent: Generate Odor Sequences for Movies Based on Large Language Model

Numerous studies have shown that integrating scents into movies enhances viewer engagement and immersion. However, creating such olfactory experiences often requires professional perfumers to match scents, limiting their widespread use. To address this, we propose OdorAgent which combines a LLM with...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Conference on Virtual Reality and 3D User Interfaces. Online) S. 105 - 114
Hauptverfasser: Zhang, Yu, Gao, Peizhong, Kang, Fangzhou, Li, Jiaxiang, Liu, Jiacheng, Lu, Qi, Xu, Yingqing
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 16.03.2024
Schlagworte:
Human-centered computing
Interaction design
Olfactory
Solid modeling
Systems and tools for interaction design
Three-dimensional displays
User interfaces
Virtual reality
Visualization
ISSN:2642-5254
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Numerous studies have shown that integrating scents into movies enhances viewer engagement and immersion. However, creating such olfactory experiences often requires professional perfumers to match scents, limiting their widespread use. To address this, we propose OdorAgent which combines a LLM with a text-image model to automate video-odor matching. The generation framework is in four dimensions: subject matter, emotion, space, and time. We applied it to a specific movie and conducted user studies to evaluate and compare the effectiveness of different system elements. The results indicate that OdorAgent possesses significant scene adaptability and enables inexperienced individuals to design odor experiences for video and images.
ISSN:2642-5254
DOI:10.1109/VR58804.2024.00034